Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation

by   Chen Dan, et al.

We study the low rank approximation problem of any given matrix A over R^n× m and C^n× m in entry-wise ℓ_p loss, that is, finding a rank-k matrix X such that A-X_p is minimized. Unlike the traditional ℓ_2 setting, this particular variant is NP-Hard. We show that the algorithm of column subset selection, which was an algorithmic foundation of many existing algorithms, enjoys approximation ratio (k+1)^1/p for 1< p< 2 and (k+1)^1-1/p for p> 2. This improves upon the previous O(k+1) bound for p> 1<cit.>. We complement our analysis with lower bounds; these bounds match our upper bounds up to constant 1 when p≥ 2. At the core of our techniques is an application of Riesz-Thorin interpolation theorem from harmonic analysis, which might be of independent interest to other algorithmic designs and analysis more broadly. As a consequence of our analysis, we provide better approximation guarantees for several other algorithms with various time complexity. For example, to make the algorithm of column subset selection computationally efficient, we analyze a polynomial time bi-criteria algorithm which selects O(klog m) columns. We show that this algorithm has an approximation ratio of O((k+1)^1/p) for 1< p< 2 and O((k+1)^1-1/p) for p> 2. This improves over the best-known bound with an O(k+1) approximation ratio. Our bi-criteria algorithm also implies an exact-rank method in polynomial time with a slightly larger approximation ratio.


page 1

page 2

page 3

page 4


Optimal ℓ_1 Column Subset Selection and a Fast PTAS for Low Rank Approximation

We study the problem of entrywise ℓ_1 low rank approximation. We give th...

Low-rank approximation in the Frobenius norm by column and row subset selection

A CUR approximation of a matrix A is a particular type of low-rank appro...

Regularized Weighted Low Rank Approximation

The classical low rank approximation problem is to find a rank k matrix ...

Towards a Zero-One Law for Entrywise Low Rank Approximation

There are a number of approximation algorithms for NP-hard versions of l...

Improved guarantees and a multiple-descent curve for the Column Subset Selection Problem and the Nyström method

The Column Subset Selection Problem (CSSP) and the Nyström method are am...

Fair Column Subset Selection

We consider the problem of fair column subset selection. In particular, ...

Quantitative Group Testing and the rank of random matrices

Given a random Bernoulli matrix A∈{0,1}^m× n, an integer 0< k < n and th...

Please sign up or login with your details

Forgot password? Click here to reset